ffmpeg sws_scale got distorted image from YUV420P to RGB24

Question

I got distorted image when try to convert YUV420p to RGB24 using sws_scale.

Code:

ret = avcodec_decode_video2(video_dec_ctx, frame, got_frame, &pkt);
if (ret < 0) {
    fprintf(stderr, "Error decoding video frame\n");
    return ret;
}
if (*got_frame) 
{
    printf("video_frame%s n:%d coded_n:%d pts:%s\n",
               cached ? "(cached)" : "",
               video_frame_count++, frame->coded_picture_number,
               "#"/*av_ts2timestr(frame->pts, &video_dec_ctx->time_base)*/);
    /* copy decoded frame to destination buffer:
     * this is required since rawvideo expects non aligned data */
    av_image_copy(video_dst_data, video_dst_linesize,
                  (const uint8_t **)(frame->data), frame->linesize,
                  video_dec_ctx->pix_fmt, video_dec_ctx->width, video_dec_ctx->height);
    /* write to rawvideo file */
    fwrite(video_dst_data[0], 1, video_dst_bufsize, video_dst_file);

    AVPicture pic;
    avpicture_alloc( &pic, AV_PIX_FMT_RGB24, frame->width, frame->height);
    SwsContext *ctxt = sws_getContext(frame->width, frame->height, static_cast<AVPixelFormat>(frame->format),
        frame->width, frame->height, AV_PIX_FMT_RGB24, SWS_BILINEAR, NULL, NULL, NULL);
    if ( NULL == ctxt )
    {
       //Log("failed to get sws context");
    }

    if ( 0 < sws_scale(ctxt, frame->data, frame->linesize, 0, frame->height, pic.data, pic.linesize))
    {
        char szPic[256] = { 0 };
        sprintf( szPic, "decoded/%d.bmp", video_frame_count );
        FILE *pf = fopen(szPic,"w");
        if ( NULL != pf )
        {
            BITMAPFILEHEADER bmpFileHeader = {0};
            bmpFileHeader.bfReserved1 = 0;
            bmpFileHeader.bfReserved2 = 0;
            bmpFileHeader.bfType = 0x4D42;
            bmpFileHeader.bfSize = sizeof(bmpFileHeader) + sizeof(BITMAPINFOHEADER) + pic.linesize[0] * frame->height;
            bmpFileHeader.bfOffBits = sizeof(bmpFileHeader) + sizeof(BITMAPINFOHEADER);
            BITMAPINFOHEADER bmiHeader = { 0 };
            bmiHeader.biSize = sizeof(BITMAPINFOHEADER);
            bmiHeader.biWidth = frame->width;
            bmiHeader.biHeight = 0 - frame->height;
            bmiHeader.biPlanes = 1;
            bmiHeader.biBitCount = 24;
            bmiHeader.biCompression = BI_RGB;
            bmiHeader.biSizeImage = pic.linesize[0] * frame->height;
            bmiHeader.biXPelsPerMeter = 0;
            bmiHeader.biYPelsPerMeter = 0;
            bmiHeader.biClrUsed = 0;
            bmiHeader.biClrImportant = 0;
            fwrite( &bmpFileHeader, 1, sizeof(bmpFileHeader), pf );
            fwrite( &bmiHeader, 1, sizeof(bmiHeader), pf );
            fwrite( pic.data[0], 1, pic.linesize[0] * frame->height, pf );
            fclose( pf );
        }
    }
    // pic.data[0] now contains the image data in RGB format (3 bytes)
    // and pic.linesize[0] is the pitch of the data (ie. size of a row in memory, which can be larger than width*sizeof(pixel))


    avpicture_free(&pic);
    sws_freeContext(ctxt);
}

above only decode frame then convert this from to RGB24, then write a bitmap. original video frame like this, but converted image, is there missing some code or some code is wrong?

thanks in advance.

Answer 1

fwrite( pic.data[0], 1, pic.linesize[0] * frame->height, pf );

For an image of e.g. 1280x720, linesize is typically larger, e.g. 1312, so you'll be writing more data than image size if you write linesize*height. You want to write (in a loop) width pixels offset by linesize bytes:

uint8_t *ptr = pic.data[0];
for (int y = 0; y < frame->height; y++) {
    fwrite(ptr, 1, frame->width, pf);
    ptr += pic.linesize[0];
}

And then it should work correctly.